mARC: Memory by Association and Reinforcement of Contexts
원문 초록
This paper introduces the memory by Association and Reinforcement of Contexts (mARC). mARC is a novel data modeling technology rooted in the second quantization formulation of quantum mechanics. It is an all-purpose incremental and unsupervised data storage and retrieval system which can be applied to all types of signal or data, structured or unstructured, textual or not. mARC can be applied to a wide range of information clas-sification and retrieval problems like e-Discovery or contextual navigation. It can also for-mulated in the artificial life framework a.k.a Conway "Game Of Life" Theory. In contrast to Conway approach, the objects evolve in a massively multidimensional space. In order to start evaluating the potential of mARC we have built a mARC-based Internet search en-gine demonstrator with contextual functionality. We compare the behavior of the mARC demonstrator with Google search both in terms of performance and relevance. In the study we find that the mARC search engine demonstrator outperforms Google search by an order of magnitude in response time while providing more relevant results for some classes of queries.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation
Learning compact binary descriptors with unsupervised deep neural networks
From Roots to Rewards: Dynamic Tree Reasoning with RL
Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
Seq vs Seq: An Open Suite of Paired Encoders and Decoders
토론
이 논문과 연결된 포럼 글이 아직 없습니다.